activity
20242026
collaborators
Showing 2025Show all

9 papers · 1 filter

cs.LG2025

Continual Pre-training of MoEs: How robust is your router?

Benjamin Thérien, Charles-Étienne Joseph, Zain Sarwar +7

Sparsely-activated Mixture of Experts (MoE) transformers are promising architectures for foundation models. Compared to dense transformers that require the same amount of floating-…

cs.CV2025

CAVE: Detecting and Explaining Commonsense Anomalies in Visual Environments

Rishika Bhagwatkar, Syrielle Montariol, Angelika Romanou +3

Humans can naturally identify, reason about, and explain anomalies in their environment. In computer vision, this long-standing challenge remains limited to industrial defects or u…

cs.LG2025

Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training

Vaibhav Singh, Paul Janson, Paria Mehrbod +4

The ever-growing availability of unlabeled data presents both opportunities and challenges for training artificial intelligence systems. While self-supervised learning (SSL) has em…

cs.LG2025

Warming Up for Zeroth-Order Federated Pre-Training with Low Resource Clients

Gwen Legate, Irina Rish, Eugene Belilovsky

Federated learning enables collaborative model training across numerous edge devices without requiring participants to share data; however, memory and communication constraints on…

cs.LG2025

A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy

Maxime Heuillet, Rishika Bhagwatkar, Jonas Ngnawé +6

Deep learning models operating in the image domain are vulnerable to small input perturbations. For years, robustness to such perturbations was pursued by training models from scra…

cs.CV2025

CHIRP: A Fine-Grained Benchmark for Open-Ended Response Evaluation in Vision-Language Models

Alexis Roger, Prateek Humane, Daniel Z. Kaplan +7

The proliferation of Vision-Language Models (VLMs) in the past several years calls for rigorous and comprehensive evaluation methods and benchmarks. This work analyzes existing VLM…